Citation

Kairanbay, Magzhan and See, John and Wong, Lai Kuan and Hii, Yong Lian (2017) Filling the gaps: Reducing the complexity of networks for multi-attribute image aesthetic prediction. In: 2017 IEEE International Conference on Image Processing (ICIP), 17-20 Sept. 2017, Beijing, China.

Text 15.pdf - Published Version Restricted to Repository staff only Download (964kB)

Abstract

Computational aesthetics have seen much progress in recent years with the increasing popularity of deep learning methods. In this paper, we present two approaches that leverage on the benefits of using Global Average Pooling (GAP) to reduce the complexity of deep convolutional neural networks. The first model fine-tunes a standard CNN with a newly introduced GAP layer. The second approach extracts global and local CNN codes by reducing the dimensionality of convolution layers with individual GAP operations. We also extend these approaches to a multi-attribute network which uses a style network to regularize the aesthetic network. Experiments demonstrate the capability of attaining comparable accuracy results while reducing training complexity substantially

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Neural network, global average pooling, multi-attribute network
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Divisions:	Faculty of Computing and Informatics (FCI)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	29 Mar 2021 18:27
Last Modified:	29 Mar 2021 18:27
URII:	http://shdl.mmu.edu.my/id/eprint/7556

Downloads

Edit (login required)